Skip to content
← Back to explorer

HFEPX Hub

Automatic Metrics + General + Long Horizon Papers

Updated from current HFEPX corpus (Apr 12, 2026). 72 papers are grouped in this hub page.

Read Full Context

Updated from current HFEPX corpus (Apr 12, 2026). 72 papers are grouped in this hub page. Common evaluation modes: Automatic Metrics, Simulation Env. Most common rater population: Domain Experts. Common annotation unit: Trajectory. Frequent quality control: Calibration. Frequently cited benchmark: BrowseComp. Common metric signal: accuracy. Use this page to compare protocol setup, judge behavior, and labeling design decisions before running new eval experiments. Newest paper in this set is from Apr 8, 2026.

Papers: 72 Last published: Apr 8, 2026 Global RSS Tag RSS
Automatic MetricsGeneralLong Horizon

Researcher Quick Triage

This hub is best used for protocol triage and replication planning from abstract-level evidence. Quality band: High .

Analysis blocks below are computed from the currently loaded sample (60 of 72 total papers in this hub).

High-Signal Coverage

100.0%

60 / 60 sampled papers are not low-signal flagged.

Replication-Ready Set

21

Benchmark + metric + eval mode explicitly present.

Judge/Human Comparability

0

Papers containing both `human_eval` and `llm_as_judge`.

  • 21 papers are replication-ready (benchmark + metric + explicit evaluation mode).
  • 0 papers support judge-vs-human agreement analysis.
  • 1 papers report explicit quality controls (calibration/adjudication/IAA).

Primary action: Start with the top 2 papers in “Start Here”, then validate assumptions in the protocol matrix.

Need evaluators for this research workflow?

Post a Job →

Why This Matters For Eval Research

  • 11.1% of papers report explicit human-feedback signals, led by pairwise preferences.
  • automatic metrics appears in 100% of papers in this hub.
  • BrowseComp is a recurring benchmark anchor for cross-paper comparisons in this page.

Protocol Takeaways

  • Most common quality-control signal is rater calibration (1.4% of papers).
  • Rater context is mostly domain experts, and annotation is commonly trajectory-level annotation; use this to scope replication staffing.
  • Compare papers that report both human_eval and llm_as_judge to quantify judge-human agreement drift.

Benchmark Interpretation

  • BrowseComp appears in 4.2% of hub papers (3/72); use this cohort for benchmark-matched comparisons.
  • HotpotQA appears in 4.2% of hub papers (3/72); use this cohort for benchmark-matched comparisons.

Metric Interpretation

  • accuracy is reported in 47.2% of hub papers (34/72); compare with a secondary metric before ranking methods.
  • cost is reported in 20.8% of hub papers (15/72); compare with a secondary metric before ranking methods.
Researcher Checklist (Expanded)

Researcher Checklist

  • Gap: Papers with explicit human feedback

    Coverage is a replication risk (11.1% vs 45% target).

  • Gap: Papers reporting quality controls

    Coverage is a replication risk (1.4% vs 30% target).

  • Moderate: Papers naming benchmarks/datasets

    Coverage is usable but incomplete (29.2% vs 35% target).

  • Strong: Papers naming evaluation metrics

    Coverage is strong (97.2% vs 35% target).

  • Gap: Papers with known rater population

    Coverage is a replication risk (5.6% vs 35% target).

  • Strong: Papers with known annotation unit

    Coverage is strong (38.9% vs 35% target).

Strengths

  • Contains both human-eval and LLM-as-judge protocols for head-to-head methodology comparison.
  • Agentic evaluation appears in 100% of papers.

Known Gaps

  • Only 1.4% of papers report quality controls; prioritize calibration/adjudication evidence.
  • Rater population is under-specified (5.6% coverage).
  • LLM-as-judge appears without enough inter-annotator agreement reporting.

Suggested Next Analyses

  • Compare papers that report both human_eval and llm_as_judge to quantify judge-human agreement drift.
  • Stratify by benchmark (BrowseComp vs HotpotQA) before comparing methods.
  • Track metric sensitivity by reporting both accuracy and cost.
  • Add inter-annotator agreement checks when reproducing these protocols.
Recommended Queries (Expanded)

Recommended Queries

Start with These 3

Use these when you need one protocol anchor, one benchmark anchor, and one recent comparison point before reading the wider hub.

Start Here (Best First 6)

Ranked for protocol completeness (human signal, benchmark + metric anchors, quality controls, and judge/human overlap).

Protocol Matrix (Top 12)

Use this to quickly compare protocol ingredients instead of scanning long prose.

Paper HF Signal Eval Modes Benchmarks Metrics QC
TraceSafe: A Systematic Assessment of LLM Guardrails on Multi-Step Tool-Calling Trajectories

Apr 8, 2026

Yes Automatic Metrics Tracesafe Bench Accuracy Not Reported
PEARL: Self-Evolving Assistant for Time Management with Reinforcement Learning

Jan 17, 2026

Yes Automatic Metrics Calconflictbench Error rate Not Reported
Signals: Trajectory Sampling and Triage for Agentic Interactions

Apr 1, 2026

Yes Automatic Metrics Not Reported Cost Not Reported
Learning When to Act: Interval-Aware Reinforcement Learning with Predictive Temporal Structure

Mar 23, 2026

Yes Automatic Metrics Not Reported Kappa Not Reported
MemMachine: A Ground-Truth-Preserving Memory System for Personalized AI Agents

Apr 6, 2026

No
Not Reported
Automatic Metrics HotpotQA Accuracy , Recall Not Reported
OSCAR: Orchestrated Self-verification and Cross-path Refinement

Apr 2, 2026

No
Not Reported
Automatic Metrics RAGTruth , HotpotQA Accuracy Not Reported
Asymmetric Actor-Critic for Multi-turn LLM Agents

Mar 31, 2026

No
Not Reported
Automatic Metrics Userbench Task success Not Reported
EnterpriseLab: A Full-Stack Platform for developing and deploying agents in Enterprises

Mar 23, 2026

No
Not Reported
Automatic Metrics Enterprisearena , Enterprisebench Cost Not Reported
PASK: Toward Intent-Aware Proactive Agents with Long-Term Memory

Apr 9, 2026

No
Not Reported
Automatic Metrics Latentneeds Bench Precision , Latency Not Reported
Full-Duplex-Bench-v3: Benchmarking Tool Use for Full-Duplex Voice Agents Under Real-World Disfluency

Apr 6, 2026

No
Not Reported
Automatic Metrics Full Duplex Bench Accuracy , Pass@1 Not Reported
$\texttt{YC-Bench}$: Benchmarking AI Agents for Long-Term Planning and Consistent Execution

Apr 1, 2026

No
Not Reported
Automatic Metrics Yc Bench Cost , Inference cost Not Reported
Training LLMs for Multi-Step Tool Orchestration with Constrained Data Synthesis and Graduated Rewards

Mar 25, 2026

No
Not Reported
Automatic Metrics Complexfuncbench Accuracy Not Reported

Protocol Diff (Top Papers)

Fast side-by-side comparison for the highest-ranked papers in this hub.

Signal TraceSafe: A Systematic Assessment of LLM Guardrail… PEARL: Self-Evolving Assistant for Time Management… Signals: Trajectory Sampling and Triage for Agentic…
Human Feedback Red TeamPairwise PreferencePairwise Preference
Evaluation Modes Automatic MetricsAutomatic MetricsAutomatic Metrics
Benchmarks Tracesafe BenchCalconflictbenchNot reported
Metrics AccuracyError rateCost
Quality Controls Not reportedNot reportedNot reported
Rater Population UnknownUnknownUnknown
Annotation Unit TrajectoryRankingTrajectory
Suggested Reading Order (Extended)

This section is intentionally expanded only when needed; use “Start Here” above for a faster pass.

Suggested Reading Order

  1. Verify Before You Commit: Towards Faithful Reasoning in LLM Agents via Self-Auditing

    Start here for detailed protocol reporting and quality-control evidence. Signals: automatic metrics. Focus: faithfulness. Abstract: In large language model (LLM) agents, reasoning trajectories are treated as reliable internal.

  2. PASK: Toward Intent-Aware Proactive Agents with Long-Term Memory

    Start here for detailed protocol reporting and quality-control evidence. Signals: automatic metrics. Focus: Latentneeds-Bench / precision. Abstract: Proactivity is a core expectation for AGI.

  3. TraceSafe: A Systematic Assessment of LLM Guardrails on Multi-Step Tool-Calling Trajectories

    Start here for detailed protocol reporting and quality-control evidence. Signals: automatic metrics + red-team protocols. Focus: Tracesafe-Bench / accuracy. Abstract: As large language models (LLMs) evolve from static.

  4. Beyond Rows to Reasoning: Agentic Retrieval for Multimodal Spreadsheet Understanding and Editing

    Include a human-eval paper to calibrate against judge-based evaluation settings. Signals: human evaluation. Focus: Frtr-Bench / accuracy. Abstract: Supported by over 200 hours of expert human evaluation, BRTR.

  5. Mind the Shift: Decoding Monetary Policy Stance from FOMC Statements with Large Language Models

    Include an LLM-as-judge paper to test judge design and agreement assumptions. Signals: LLM-as-judge. Focus: accuracy. Abstract: We introduce Delta-Consistent Scoring (DCS), an annotation-free framework that maps frozen large.

  6. PEARL: Self-Evolving Assistant for Time Management with Reinforcement Learning

    Adds automatic metrics with pairwise preferences for broader protocol coverage within this hub. Signals: automatic metrics + pairwise preferences. Focus: Calconflictbench / error rate. Abstract: We refer to.

  7. Error Notebook-Guided, Training-Free Part Retrieval in 3D CAD Assemblies via Vision-Language Models

    Adds automatic metrics with pairwise preferences for broader protocol coverage within this hub. Signals: automatic metrics + pairwise preferences. Focus: accuracy. Abstract: We additionally contribute a CAD dataset.

  8. Signals: Trajectory Sampling and Triage for Agentic Interactions

    Adds automatic metrics with pairwise preferences for broader protocol coverage within this hub. Signals: automatic metrics + pairwise preferences. Focus: cost. Abstract: In a controlled annotation study on.

Known Limitations

Known Limitations

  • Only 1.4% of papers report quality controls; prioritize calibration/adjudication evidence.
  • Rater population is under-specified (5.6% coverage).
  • Narrative synthesis is grounded in metadata and abstracts only; full-paper implementation details are not parsed.
Research Utility Snapshot (Detailed)

Research Utility Snapshot

Human Feedback Mix

  • Pairwise Preference (6)
  • Demonstrations (1)
  • Red Team (1)

Evaluation Modes

  • Automatic Metrics (72)
  • Simulation Env (2)
  • Human Eval (1)
  • Llm As Judge (1)

Top Benchmarks

  • BrowseComp (3)
  • HotpotQA (3)
  • Ama Bench (1)
  • APPS (1)

Top Metrics

  • Accuracy (34)
  • Cost (15)
  • Latency (8)
  • F1 (7)

Rater Population Mix

  • Domain Experts (4)

Quality Controls

  • Calibration (1)
Coverage diagnostics (sample-based): human-feedback 13.3% · benchmarks 35.0% · metrics 98.3% · quality controls 1.7%.

Top Papers

Related Hubs

Get Started

Join the #1 Platform for AI Training Talent

Where top AI builders and expert AI Trainers connect to build the future of AI.
Self-Service
Post a Job
Post your project and get a shortlist of qualified AI Trainers and Data Labelers. Hire and manage your team in the tools you already use.
Managed Service
For Large Projects
Done-for-You
We recruit, onboard, and manage a dedicated team inside your tools. End-to-end operations for large or complex projects.
For Freelancers
Join as an AI Trainer
Find AI training and data labeling projects across platforms, all in one place. One profile, one application process, more opportunities.